Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.4647. Min Act: -0.1700
Data Index: 5977407 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.2772. Min Act: -0.1700
Data Index: 3079729 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.2772. Min Act: -0.1700
Data Index: 2249870 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.1522. Min Act: -0.1700
Data Index: 6399346 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.1522. Min Act: -0.1700
Data Index: 5647842 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.1522. Min Act: -0.1700
Data Index: 8290133 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.1522. Min Act: -0.1700
Data Index: 6638490 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.0897. Min Act: -0.1700
Data Index: 5685426 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.0272. Min Act: -0.1700
Data Index: 3504631 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.0272. Min Act: -0.1700
Data Index: 6774128 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4647. Min Range: -9.4647
Max Act: 9.0272. Min Act: -0.1700
Data Index: 2832541 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 1817203 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 1356886 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 5522050 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 2032294 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 756282 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 6071630 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9647. Min Act: -0.1700
Data Index: 6334291 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9022. Min Act: -0.1700
Data Index: 6029526 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4647. Min Range: -9.4647
Max Act: 8.9022. Min Act: -0.1700
Data Index: 5567642 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19